Grep or Embeddings? Agentic Enterprise Document Search

AI Engineer23m 21s
0 comments · 0 votesOpen discussionClose discussion
Sign in to join the discussion

    Video summary

    George He compares local file traversal with pre-indexed retrieval, explaining why a coding repository's structure does not transfer neatly to a large enterprise document collection. He describes scale, mixed file formats, token costs and permission metadata as reasons to combine keyword and semantic retrieval with an agent's ability to inspect specific files.

    The talk breaks document search into locating relevant material, traversing metadata, finding exact text and reading rendered content. George He emphasizes structured parsing and page screenshots for tables, diagrams and scanned documents, then addresses synchronization, freshness and storage tradeoffs.

    A demonstration uses a prepared collection of Alphabet financial reports to show how hybrid search, grep-like tools and contextual reading can ground a cash-flow answer across several documents. George He presents the harness and its tool primitives as the bridge between finding candidate information and producing a traceable result.

    Original YouTube thumbnailWatch on YouTube

    Share this page

    George He against a black background beside the blue-and-white headline “GREP OR EMBEDDINGS?”. Framed in blue with WWW.ARTIFICIAL-INTELLIGENCE.VIDEO, 7 October 2026 and duration 23m 21s.

    George He argues that enterprise document agents need hybrid retrieval, useful file tools and reliable parsing rather than a blanket choice between grep and embeddings.